requirements

app.py

@@ -1,18 +1,23 @@
 import gradio as gr
-from transformers import AutoTokenizer, AutoModelForDocumentQuestionAnswering
+from transformers import AutoProcessor, AutoModelForDocumentQuestionAnswering
 from PIL import Image
 
-tokenizer = AutoTokenizer.from_pretrained("impira/layoutlm-invoices")
+# Load processor and model
+processor = AutoProcessor.from_pretrained("impira/layoutlm-invoices")
 model = AutoModelForDocumentQuestionAnswering.from_pretrained("impira/layoutlm-invoices")
 
 def answer_question(image, question):
-    inputs = tokenizer(image, question, return_tensors="pt")
+    # Ensure RGB mode
+    if image.mode != "RGB":
+        image = image.convert("RGB")
+
+    inputs = processor(image, question, return_tensors="pt")
     outputs = model(**inputs)
-    start_logits = outputs.start_logits
-    end_logits = outputs.end_logits
-    start = start_logits.argmax(-1).item()
-    end = end_logits.argmax(-1).item() + 1
-    answer = tokenizer.decode(inputs.input_ids[0][start:end])
+
+    start = outputs.start_logits.argmax(-1).item()
+    end = outputs.end_logits.argmax(-1).item() + 1
+
+    answer = processor.tokenizer.decode(inputs["input_ids"][0][start:end])
     return answer
 
 iface = gr.Interface(